metadata
library_name: transformers
language:
- kh
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- seanghay/khmer_mpwt_speech
metrics:
- wer
model-index:
- name: Whisper Small - KH
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: seanghay/khmer_mpwt_speech
type: seanghay/khmer_mpwt_speech
args: 'config: kh, split: test'
metrics:
- name: Wer
type: wer
value: 58.29787234042553
Whisper Small - KH
This model is a fine-tuned version of openai/whisper-small on the seanghay/khmer_mpwt_speech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3627
- Wer: 58.2979
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7064 | 1.3966 | 250 | 0.7823 | 106.1170 |
| 0.4618 | 2.7933 | 500 | 0.5052 | 78.0851 |
| 0.1901 | 4.1899 | 750 | 0.4079 | 64.7340 |
| 0.1137 | 5.5866 | 1000 | 0.3627 | 58.2979 |
Framework versions
- Transformers 5.15.0
- Pytorch 2.11.0+cu128
- Datasets 5.0.1
- Tokenizers 0.22.2